{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KOJK63RKF4QCD5XJYN356LJTA2","short_pith_number":"pith:KOJK63RK","schema_version":"1.0","canonical_sha256":"5392af6e2a2f2021f6e9c377df2d330693d106e38d33e5d0184f47889bc9d696","source":{"kind":"arxiv","id":"1511.05432","version":3},"attestation_state":"computed","paper":{"title":"Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Sahand Negahban, Uri Shaham, Yutaro Yamada","submitted_at":"2015-11-17T15:14:57Z","abstract_excerpt":"We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-maximization procedure, in which the loss of the network is minimized over perturbed examples that are generated at each parameter update. We show that adversarial training of ANNs is in fact robustification of the network optimization, and that our proposed framework generalizes previous approaches for increasing local stability of ANNs. Experimental results reveal that our approach increases the robustness of the ne"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1511.05432","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-17T15:14:57Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"69839e14bbf060241355031f88955872e96af54643e296432d1aa1613b58ea31","abstract_canon_sha256":"431e9ea601dc2ec0210aeb0f099e4102e9332c7aa557907eeb76f056946a14b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:50.982201Z","signature_b64":"pKpoBpcykqjECKcJmUkqP9SOlogjKRa4SLT8IUATjUlKWindAGc9ulfMXaYLeq1j/onSLemLFZDrx/bux36VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5392af6e2a2f2021f6e9c377df2d330693d106e38d33e5d0184f47889bc9d696","last_reissued_at":"2026-05-18T00:16:50.981587Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:50.981587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Sahand Negahban, Uri Shaham, Yutaro Yamada","submitted_at":"2015-11-17T15:14:57Z","abstract_excerpt":"We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-maximization procedure, in which the loss of the network is minimized over perturbed examples that are generated at each parameter update. We show that adversarial training of ANNs is in fact robustification of the network optimization, and that our proposed framework generalizes previous approaches for increasing local stability of ANNs. Experimental results reveal that our approach increases the robustness of the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05432","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1511.05432","created_at":"2026-05-18T00:16:50.981673+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05432v3","created_at":"2026-05-18T00:16:50.981673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05432","created_at":"2026-05-18T00:16:50.981673+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOJK63RKF4QC","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOJK63RKF4QCD5XJ","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOJK63RK","created_at":"2026-05-18T12:29:29.992203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1609.04836","citing_title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2","json":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2.json","graph_json":"https://pith.science/api/pith-number/KOJK63RKF4QCD5XJYN356LJTA2/graph.json","events_json":"https://pith.science/api/pith-number/KOJK63RKF4QCD5XJYN356LJTA2/events.json","paper":"https://pith.science/paper/KOJK63RK"},"agent_actions":{"view_html":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2","download_json":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2.json","view_paper":"https://pith.science/paper/KOJK63RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05432&json=true","fetch_graph":"https://pith.science/api/pith-number/KOJK63RKF4QCD5XJYN356LJTA2/graph.json","fetch_events":"https://pith.science/api/pith-number/KOJK63RKF4QCD5XJYN356LJTA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2/action/storage_attestation","attest_author":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2/action/author_attestation","sign_citation":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2/action/citation_signature","submit_replication":"https://pith.science/pith/KOJK63RKF4QCD5XJYN356LJTA2/action/replication_record"}},"created_at":"2026-05-18T00:16:50.981673+00:00","updated_at":"2026-05-18T00:16:50.981673+00:00"}